© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Andy Arditi · GPT-OSS BatchTopK SAEs
    5. GPT-OSS-20B
    7. Resid Post - 131k
    9. 11-RESID-POST-AA
    11. 108501
    Prev
    Next
    INDEX
    Explanations

    love your neighbor as yourself

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_11/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    redo
    -0.09
    UST
    -0.08
    Low
    -0.08
     Pounds
    -0.08
    retain
    -0.07
    备案
    -0.07
     retain
    -0.07
    LAB
    -0.07
    slos
    -0.07
     Oven
    -0.07
    POSITIVE LOGITS
     compassion
    0.09
     doctrine
    0.09
     दूस
    0.09
     scripture
    0.09
     interpersonal
    0.08
     principe
    0.08
    伦理
    0.08
     Doctrine
    0.08
     principle
    0.08
    666
    0.08
    Activations Density 0.007%

    No Known Activations